Conditional $β$-VAE for De Novo Molecular Generation

2022-05-01 · Ryan J Richards, Austen M Groener

Deep learning has significantly advanced and accelerated de novo molecular generation. Generative networks, namely Variational Autoencoders (VAEs) can not only randomly generate new molecules, but also alter molecular structures to optimize specific chemical properties which are pivotal for drug-discovery. While VAEs have been proposed and researched in the past for pharmaceutical applications, they possess deficiencies which limit their ability to both optimize properties and decode syntactically valid molecules. We present a recurrent, conditional $\beta$-VAE which disentangles the latent space to enhance post hoc molecule optimization. We create a mutual information driven training protocol and data augmentations to both increase molecular validity and promote longer sequence generation. We demonstrate the efficacy of our framework on the ZINC-250k dataset, achieving SOTA unconstrained optimization results on the penalized LogP (pLogP) and QED scores, while also matching current SOTA results for validity, novelty and uniqueness scores for random generation. We match the current SOTA on QED for top-3 molecules at 0.948, while setting a new SOTA for pLogP optimization at 104.29, 90.12, 69.68 and demonstrating improved results on the constrained optimization task.

📄 PDF Abstract BibTeX arXiv:2205.01592

Code (0)

등록된 구현이 없습니다.

Tasks

Drug Discoveryvalid

Methods 이 논문이 사용한 방법론

HOC 설명 없음

Molecular generative model based on conditional variational autoencoder for de novo molecular design

2018-06-15 · Jaechang Lim, Seongok Ryu, Jin Woo Kim, Woo Youn Kim

We propose a molecular generative model based on the conditional variational autoencoder for de novo molecular design. It is specialized to control multiple molecular properties simultaneously by imposing them on a laten…

Conditional β-VAE for De Novo Molecular Generation

2022-05-02 · ChemRxiv 2022 5 · Ryan J Richards, Austen M Groener

Drug Discovery Molecular Graph Generation valid

MetaMolGen: A Neural Graph Motif Generation Model for De Novo Molecular Design

2025-04-22 · Zimo Yan, Jie Zhang, Zheng Xie, Chang Liu 외

Molecular generation plays an important role in drug discovery and materials science, especially in data-scarce scenarios where traditional generative models often struggle to achieve satisfactory conditional generalizat…

Drug Discovery Meta-Learning valid

Diffusion Models in $\textit{De Novo}$ Drug Design

2024-06-07 · Amira Alakhdar, Barnabas Poczos, Newell Washburn

Diffusion models have emerged as powerful tools for molecular generation, particularly in the context of 3D molecular structures. Inspired by non-equilibrium statistical physics, these models can generate 3D molecular st…

Computational chemistry Denoising Drug Design Drug Discovery+1

Learning Disentangled Equivariant Representation for Explicitly Controllable 3D Molecule Generation

2024-12-19 · Haoran Liu, Youzhi Luo, Tianxiao Li, James Caverlee 외

We consider the conditional generation of 3D drug-like molecules with \textit{explicit control} over molecular properties such as drug-like properties (e.g., Quantitative Estimate of Druglikeness or Synthetic Accessibili…

3D Molecule Generation Drug Discovery